arXiv subjects

Sakib Mahmud Khan

Publications and source records attributed to Sakib Mahmud Khan.

At least 19 recordsLinked to original sources

arXiv2025

An Overview of Automated Vehicle Longitudinal Platoon Formation Strategies

Automated vehicle (AV) platooning has the potential to improve the safety, operational, and energy efficiency of surface transportation systems by limiting or eliminating human involvement in the driving tasks. The theoretical validity of the AV platooning strategies has been established and practical applications are being tested under real-world conditions. The emergence of sensors, communication, and control strategies has resulted in rapid and constant evolution of AV platooning strategies. In this paper, we review the state-of-the-art knowledge in AV longitudinal platoon formation using a five-component platooning framework, which includes vehicle model, information-receiving process, information flow topology, spacing policy, and controller and discuss the advantages and limitations of the components. Based on the discussion about existing strategies and associated limitations, potential future research directions are presented.

eess.SY↗

arXiv2025

Quantum Computing Supported Adversarial Attack-Resilient Autonomous Vehicle Perception Module for Traffic Sign Classification

Deep learning (DL)-based image classification models are essential for autonomous vehicle (AV) perception modules since incorrect categorization might have severe repercussions. Adversarial attacks are widely studied cyberattacks that can lead DL models to predict inaccurate output, such as incorrectly classified traffic signs by the perception module of an autonomous vehicle. In this study, we create and compare hybrid classical-quantum deep learning (HCQ-DL) models with classical deep learning (C-DL) models to demonstrate robustness against adversarial attacks for perception modules. Before feeding them into the quantum system, we used transfer learning models, alexnet and vgg-16, as feature extractors. We tested over 1000 quantum circuits in our HCQ-DL models for projected gradient descent (PGD), fast gradient sign attack (FGSA), and gradient attack (GA), which are three well-known untargeted adversarial approaches. We evaluated the performance of all models during adversarial attacks and no-attack scenarios. Our HCQ-DL models maintain accuracy above 95\% during a no-attack scenario and above 91\% for GA and FGSA attacks, which is higher than C-DL models. During the PGD attack, our alexnet-based HCQ-DL model maintained an accuracy of 85\% compared to C-DL models that achieved accuracies below 21\%. Our results highlight that the HCQ-DL models provide improved accuracy for traffic sign classification under adversarial settings compared to their classical counterparts.

cs.LG↗

arXiv2023

Development and Evaluation of Ensemble Learning-based Environmental Methane Detection and Intensity Prediction Models

The environmental impacts of global warming driven by methane (CH4) emissions have catalyzed significant research initiatives in developing novel technologies that enable proactive and rapid detection of CH4. Several data-driven machine learning (ML) models were tested to determine how well they identified fugitive CH4 and its related intensity in the affected areas. Various meteorological characteristics, including wind speed, temperature, pressure, relative humidity, water vapor, and heat flux, were included in the simulation. We used the ensemble learning method to determine the best-performing weighted ensemble ML models built upon several weaker lower-layer ML models to (i) detect the presence of CH4 as a classification problem and (ii) predict the intensity of CH4 as a regression problem.

cs.LG↗

arXiv2023

Autonomous Vehicles for All?

The traditional build-and-expand approach is not a viable solution to keep roadway traffic rolling safely, so technological solutions, such as Autonomous Vehicles (AVs), are favored. AVs have considerable potential to increase the carrying capacity of roads, ameliorate the chore of driving, improve safety, provide mobility for those who cannot drive, and help the environment. However, they also raise concerns over whether they are socially responsible, accounting for issues such as fairness, equity, and transparency. Regulatory bodies have focused on AV safety, cybersecurity, privacy, and legal liability issues, but have failed to adequately address social responsibility. Thus, existing AV developers do not have to embed social responsibility factors in their proprietary technology. Adverse bias may therefore occur in the development and deployment of AV technology. For instance, an artificial intelligence-based pedestrian detection application used in an AV may, in limited lighting conditions, be biased to detect pedestrians who belong to a particular racial demographic more efficiently compared to pedestrians from other racial demographics. Also, AV technologies tend to be costly, with a unique hardware and software setup which may be beyond the reach of lower-income people. In addition, data generated by AVs about their users may be misused by third parties such as corporations, criminals, or even foreign governments. AVs promise to dramatically impact labor markets, as many jobs that involve driving will be made redundant. We argue that the academic institutions, industry, and government agencies overseeing AV development and deployment must act proactively to ensure that AVs serve all and do not increase the digital divide in our society.

cs.CY↗

arXiv2022

A Hybrid Defense Method against Adversarial Attacks on Traffic Sign Classifiers in Autonomous Vehicles

Adversarial attacks can make deep neural network (DNN) models predict incorrect output labels, such as misclassified traffic signs, for autonomous vehicle (AV) perception modules. Resilience against adversarial attacks can help AVs navigate safely on the road by avoiding misclassication of signs or objects. This DNN-based study develops a resilient traffic sign classifier for AVs that uses a hybrid defense method. We use transfer learning to retrain the Inception-V3 and Resnet-152 models as traffic sign classifiers. This method also utilizes a combination of three different strategies: random filtering, ensembling, and local feature mapping. We use the random cropping and resizing technique for random filtering, plurality voting as ensembling strategy and an optical character recognition model as a local feature mapper. This DNN-based hybrid defense method has been tested for the no attack scenario and against well-known untargeted adversarial attacks (e.g., Projected Gradient Descent or PGD, Fast Gradient Sign Method or FGSM, Momentum Iterative Method or MIM attack, and Carlini and Wagner or C&W). We find that our hybrid defense method achieves 99% average traffic sign classification accuracy for the no attack scenario and 88% average traffic sign classification accuracy for all attack scenarios. Moreover, the hybrid defense method, presented in this study, improves the accuracy for traffic sign classification compared to the traditional defense methods (i.e., JPEG filtering, feature squeezing, binary filtering, and random filtering) up to 6%, 50%, and 55% for FGSM, MIM, and PGD attacks, respectively.

cs.CR↗

arXiv2021

Hybrid Quantum-Classical Neural Network for Cloud-supported In-Vehicle Cyberattack Detection

A classical computer works with ones and zeros, whereas a quantum computer uses ones, zeros, and superpositions of ones and zeros, which enables quantum computers to perform a vast number of calculations simultaneously compared to classical computers. In a cloud-supported cyber-physical system environment, running a machine learning application in quantum computers is often difficult, due to the existing limitations of the current quantum devices. However, with the combination of quantum-classical neural networks (NN), complex and high-dimensional features can be extracted by the classical NN to a reduced but more informative feature space to be processed by the existing quantum computers. In this study, we develop a hybrid quantum-classical NN to detect an amplitude shift cyber-attack on an in-vehicle control area network (CAN) dataset. We show that using the hybrid quantum classical NN, it is possible to achieve an attack detection accuracy of 94%, which is higher than a Long short-term memory (LSTM) NN (87%) or quantum NN alone (62%)

cs.LG↗

arXiv2021

Efficacy of Statistical and Artificial Intelligence-based False Information Cyberattack Detection Models for Connected Vehicles

Connected vehicles (CVs), because of the external connectivity with other CVs and connected infrastructure, are vulnerable to cyberattacks that can instantly compromise the safety of the vehicle itself and other connected vehicles and roadway infrastructure. One such cyberattack is the false information attack, where an external attacker injects inaccurate information into the connected vehicles and eventually can cause catastrophic consequences by compromising safety-critical applications like the forward collision warning. The occurrence and target of such attack events can be very dynamic, making real-time and near-real-time detection challenging. Change point models, can be used for real-time anomaly detection caused by the false information attack. In this paper, we have evaluated three change point-based statistical models; Expectation Maximization, Cumulative Summation, and Bayesian Online Change Point Algorithms for cyberattack detection in the CV data. Also, data-driven artificial intelligence (AI) models, which can be used to detect known and unknown underlying patterns in the dataset, have the potential of detecting a real-time anomaly in the CV data. We have used six AI models to detect false information attacks and compared the performance for detecting the attacks with our developed change point models. Our study shows that change points models performed better in real-time false information attack detection compared to the performance of the AI models. Change point models having the advantage of no training requirements can be a feasible and computationally efficient alternative to AI models for false information attack detection in connected vehicles.

cs.CR↗

arXiv2021

Hybrid Classical-Quantum Deep Learning Models for Autonomous Vehicle Traffic Image Classification Under Adversarial Attack

Image classification must work for autonomous vehicles (AV) operating on public roads, and actions performed based on image misclassification can have serious consequences. Traffic sign images can be misclassified by an adversarial attack on machine learning models used by AVs for traffic sign recognition. To make classification models resilient against adversarial attacks, we used a hybrid deep-learning model with both the quantum and classical layers. Our goal is to study the hybrid deep-learning architecture for classical-quantum transfer learning models to support the current era of intermediate-scale quantum technology. We have evaluated the impacts of various white box adversarial attacks on these hybrid models. The classical part of hybrid models includes a convolution network from the pre-trained Resnet18 model, which extracts informative features from a high dimensional LISA traffic sign image dataset. The output from the classical processor is processed further through the quantum layer, which is composed of various quantum gates and provides support to various quantum mechanical features like entanglement and superposition. We have tested multiple combinations of quantum circuits to provide better classification accuracy with decreasing training data and found better resiliency for our hybrid classical-quantum deep learning model during attacks compared to the classical-only machine learning models.

quant-ph↗

arXiv2021

Hybrid Quantum-Classical Neural Network for Incident Detection

The efficiency and reliability of real-time incident detection models directly impact the affected corridors' traffic safety and operational conditions. The recent emergence of cloud-based quantum computing infrastructure and innovations in noisy intermediate-scale quantum devices have revealed a new era of quantum-enhanced algorithms that can be leveraged to improve real-time incident detection accuracy. In this research, a hybrid machine learning model, which includes classical and quantum machine learning (ML) models, is developed to identify incidents using the connected vehicle (CV) data. The incident detection performance of the hybrid model is evaluated against baseline classical ML models. The framework is evaluated using data from a microsimulation tool for different incident scenarios. The results indicate that a hybrid neural network containing a 4-qubit quantum layer outperforms all other baseline models when there is a lack of training data. We have created three datasets; DS-1 with sufficient training data, and DS-2 and DS-3 with insufficient training data. The hybrid model achieves a recall of 98.9%, 98.3%, and 96.6% for DS-1, DS-2, and DS-3, respectively. For DS-2 and DS-3, the average improvement in F2-score (measures model's performance to correctly identify incidents) achieved by the hybrid model is 1.9% and 7.8%, respectively, compared to the classical models. It shows that with insufficient data, which may be common for CVs, the hybrid ML model will perform better than the classical models. With the continuing improvements of quantum computing infrastructure, the quantum ML models could be a promising alternative for CV-related applications when the available data is insufficient.

cs.LG↗

arXiv2020

Situation-Aware Left-Turning Connected and Automated Vehicle Operation at Signalized Intersections

One challenging aspect of the Connected and Automated Vehicle (CAV) operation in mixed traffic is the development of a situation-awareness module for CAVs. While operating on public roads, CAVs need to assess their surroundings, especially the intentions of non-CAVs. Generally, CAVs demonstrate a defensive driving behavior, and CAVs expect other non-autonomous entities on the road will follow the traffic rules or common driving behavior. However, the presence of aggressive human drivers in the surrounding environment, who may not follow traffic rules and behave abruptly, can lead to serious safety consequences. In this paper, we have addressed the CAV and non-CAV interaction by evaluating a situation-awareness module for left-turning CAV operations in an urban area. Existing literature does not consider the intent of the following vehicle for a CAVs left-turning movement, and existing CAV controllers do not assess the following non-CAVs intents. Based on our simulation study, the situation-aware CAV controller module reduces up to 27% of the abrupt braking of the following non-CAVs for scenarios with different opposing through movement compared to the base scenario with the autonomous vehicle, without considering the following vehicles intent. The analysis shows that the average travel time reductions for the opposite through traffic volumes of 600, 800, and 1000 vehicle/hour/lane are 58%, 52%, and 62%, respectively, for the aggressive human driver following the CAV if the following vehicles intent is considered by a CAV in making a left turn at an intersection.

cs.RO↗

arXiv2020

Is Third-Party Provided Travel Time Helpful to Estimate Freeway Performance Measures?

Transportation agencies monitor freeway performance using various measures such as VMT (Vehicle Miles Traveled), VHD (Vehicle Hours of Delay), and VHT (Vehicle Hours Traveled). Public transportation agencies typically rely on point detector data to estimate these freeway performance measures. Point detectors, such as inductive loops cannot capture the travel time for a corridor, which can lead to inaccurate performance measure estimation. This research develops a hybrid method, which estimates of freeway performance measures using a mix of probe data from third-parties and data from traditional point detectors. Using a simulated I-210 model, the overall framework using multiple data sources is evaluated, and compared with the traditional point detector-based estimation method. In the traditional method, point speeds are estimated with the flow and occupancy values using the g-factors. Data from 5% of the total vehicle are used to generate the third-party vendor provided travel time data. The analysis is conducted for multiple scenarios, including peak and off-peak periods. Findings suggest that fusing data from both third-party vendors and point detectors can help estimate performance measures better, compared to the traditional method, in scenarios that have noticeable traffic demand on freeways.

eess.SP↗

arXiv2020

An Evaluation Framework of End-to-End 5G Millimeter Wave Communication for Connected Vehicle Applications

The internet-of-things (IoT) environment connects different intelligent devices together and enables seamless data communication between the connected devices. Connected vehicles (CVs) are one of the primary example of the IoT, and the efficient, reliable, and safe operation of CVs demands a reliable wireless communication system, which can ensure high throughput and low communication latency. The 5G millimeter wave (5G mmWave) wireless communication network offers such benefits, which can be the enabler of CV applications, especially for dense urban areas with high number of CVs. In this study, we present a simulation-based evaluation framework of end-to-end 5G mmWave communication for CV applications. In addition, we compare the 5G mmWave with the Dedicated Short Range Communication (DSRC) technology for a CV application. The simulation framework is developed using two simulators, a network simulator and a traffic simulator. In order to develop the framework in this study, we have used Network Simulator 3 (ns-3) and SUMO, an open-source microscopic roadway traffic simulator. We have used end-to-end latency, packet loss and throughput as the performance evaluation metrics. We have found that for dense urban areas, 5G mmWave can achieve higher throughput, lower latency and lower data loss compared to DSRC. 5G mmWave can support CV applications with high throughput requirement on the downlink data flow. Through further investigation, we have found that the performance of 5G mmWave is significantly impacted by the penetration level of CVs, maximum CV speed, and CV application requirements.

cs.NI↗

arXiv2019

Development and evaluation of an open-source, machine learning-based average annual daily traffic estimation software

Traditionally, Departments of Transportation (DOTs) use the factor-based model to estimate Annual Average Daily Traffic (AADT) from short-term traffic counts. The expansion factors, derived from the permanent traffic count stations, are applied to the short-term counts for AADT estimation. The inherent challenges of the factor-based method (i.e., grouping the count stations, applying proper expansion factors) make the estimated AADT values erroneous. Based on a survey conducted by the authors, 97% of the 39 public transportation agencies use the factor-based AADT estimation model, and these agencies face the aforementioned challenges while using factor-based models to estimate AADT. To derive a more accurate AADT, this paper presents the "estimAADTion" software, which is an open-source software developed based on a machine learning method called support vector regression (SVR) for estimating AADT using 24-hour short-term count data. DOTs conduct short-term counts at different locations periodically. This software has been designed to estimate AADT at a particular location from the short-term counts collected at those locations. In order to estimate AADT from short-term counts, the software uses data from permanent count stations to train the SVR model. The performance of the "estimAADTion" software is validated using the short-term count data from South Carolina. The Mean Absolute Percentage Error (MAPE) of the AADT estimated from the software is 3%, while the factor-based method produces a MAPE value of 6%.

cs.SE↗

arXiv2019

Multi-class Twitter Data Categorization and Geocoding with a Novel Computing Framework

This study details the progress in transportation data analysis with a novel computing framework in keeping with the continuous evolution of the computing technology. The computing framework combines the Labelled Latent Dirichlet Allocation (L-LDA)-incorporated Support Vector Machine (SVM) classifier with the supporting computing strategy on publicly available Twitter data in determining transportation-related events to provide reliable information to travelers. The analytical approach includes analyzing tweets using text classification and geocoding locations based on string similarity. A case study conducted for the New York City and its surrounding areas demonstrates the feasibility of the analytical approach. Approximately 700,010 tweets are analyzed to extract relevant transportation-related information for one week. The SVM classifier achieves more than 85% accuracy in identifying transportation-related tweets from structured data. To further categorize the transportation-related tweets into sub-classes: incident, congestion, construction, special events, and other events, three supervised classifiers are used: L-LDA, SVM, and L-LDA incorporated SVM. Findings from this study demonstrate that the analytical framework, which uses the L-LDA incorporated SVM, can classify roadway transportation-related data from Twitter with over 98.3% accuracy, which is significantly higher than the accuracies achieved by standalone L-LDA and SVM.

cs.SI↗

arXiv2019

Synergizing Roadway Infrastructure Investment with Digital Infrastructure for Infrastructure-Based Connected Vehicle Applications: Review of Current Status and Future Directions

The safety, mobility, environmental, energy, and economic benefits of transportation systems, which are the focus of recent connected vehicle (CV) programs, are potentially dramatic. However, realization of these benefits largely hinges on the timely integration of digital technology into upcoming as well as existing transportation infrastructure. CVs must be enabled to broadcast and receive data to and from other CVs [vehicle-to-vehicle (V2V) communication], to and from infrastructure [vehicle-to-infrastructure (V2I) communication], and to and from other road users, such as bicyclists or pedestrians (vehicle-to-other road users communication). Further, the infrastructure and transportation agencies that manage V2I-focused applications must be able to collect, process, distribute, and archive these data quickly, reliably, and securely. This paper focuses on V2I applications and investigates current digital roadway infrastructure initiatives. It highlights the importance of including digital infrastructure investment alongside investment in more traditional transportation infrastructure to keep up with the auto industry push toward increasing intervehicular communication. By studying current CV testbeds and smart-city initiatives, this paper identifies digital infrastructure being used by public agencies. It also examines public agencies limited budgeting for digital infrastructure and finds that current expenditure is inadequate for realizing the potential benefits of V2I applications. Finally, the paper presents a set of recommendations, based on a review of current practices and future needs, designed to guide agencies responsible for transportation infrastructure. It stresses the importance of collaboration for establishing national and international platforms for the planning, deployment, and management of digital infrastructure to support connected transportation systems.

cs.CY↗

arXiv2019

Connected Vehicle Supported Adaptive Traffic Control for Near-congested Condition in a Mixed Traffic Stream

Connected Vehicles (CVs) have the potential to significantly increase the safety, mobility, and environmental benefits of transportation applications. In this research, we have developed a real time adaptive traffic signal control algorithm that utilizes only CV data to compute the signal timing parameters for an urban arterial in the near congested condition. We have used a machine learning based short term traffic forecasting model to predict the overall traffic counts in CV based platoons. Using a multi objective optimization technique, we compute the green interval time for each intersection using CV based platoons. Later, we dynamically adjust intersection offsets in real time, so the vehicles in the major street can experience improved operational conditions compared to loop detector based actuated coordinated signal control. Using a 3 mile long simulated corridor of US 29 in Greenville, SC, we have evaluated the performance of our CV based adaptive signal control. For the next time interval, using only 5% CV data, the Root Mean Square Error of the machine learning based prediction is 10 vehicles. Our analysis reveals that the CV based adaptive signal control improves operational conditions in the major street compared to the actuated coordinated scenario. Also, using only CV data, the operational performance improves even for a low CV penetration (5% CV), and the benefit increases with increasing CV penetration. We can provide operational benefits to both CVs and non CVs with the limited data from 5% CVs, with 5.6% average speed increase, and 66.7% and 32.4% reduction in average maximum queue length and stopped delay, respectively, in major street coordinated direction compared to the actuated coordinated scenario in the same direction.

eess.SP↗

arXiv2018

Connected Vehicle Application Development Platform (CVDeP) for Edge-centric Cyber-Physical Systems

Connected vehicle (CV) application developers need a development platform to build, test and debug CV applications, such as safety, mobility, and environmental applications, in an edge-centric Cyber-Physical Systems. Our study objective is to develop and evaluate a scalable and secure CV application development platform (CVDeP) that enables the CV application developers to build, test and debug CV applications in real-time. CVDeP ensures that the functional requirements of the CV applications meet the latency requirements imposed by corresponding CV applications. We conducted a case study to evaluate the efficacy of CVDeP using two CV applications (one safety and one mobility application) and validated them through a field evaluation at the Clemson University Connected and Autonomous Vehicle Testbed (CU-CAVT). The analysis outcome proves the efficacy of CVDeP, which satisfies the functional requirements (e.g., latency, throughput) of a CV application while maintaining scalability, and security of the platform and applications.

cs.NI↗

arXiv2018

Development and Evaluation of Recurrent Neural Network based Models for Hourly Traffic Volume and AADT Prediction

The prediction of high-resolution hourly traffic volumes of a given roadway is essential for transportation planning. Traditionally, Automatic Traffic Recorders (ATR) are used to collect this hourly volume data. These large datasets are time series data characterized by long-term temporal dependencies and missing values. Regarding the temporal dependencies, all roadways are characterized by seasonal variations that can be weekly, monthly or yearly, depending on the cause of the variation. Regarding the missing data in a time-series sequence, traditional time series forecasting models perform poorly under the influence of seasonal variations. To address this limitation, robust, Recurrent Neural Network (RNN) based, multi-step ahead forecasting models are developed for time-series in this study. The simple RNN, the Gated Recurrent Unit (GRU) and the Long Short-Term Memory (LSTM) units are used to develop the model and evaluate its performance. Two approaches are used to address the missing value issue: masking and imputation, in conjunction with the RNN models. Six different imputation algorithms are then used to identify the best model. The analysis indicates that the LSTM model performs better than simple RNN and GRU models, and imputation performs better than masking to predict future traffic volume. Based on analysis using 92 ATRs, the LSTM-Median model is deemed the best model in all scenarios for hourly traffic volume and AADT prediction, with an average RMSE of 274 and MAPE of 18.91% for hourly traffic volume prediction and average RMSE of 824 and MAPE of 2.10% for AADT prediction.

stat.AP↗